Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6321 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.9866. Min Act: -0.1700
Data Index: 6330220 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.9554. Min Act: -0.1700
Data Index: 8733028 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.9241. Min Act: -0.1700
Data Index: 3881883 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.8929. Min Act: -0.1700
Data Index: 5150279 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.8616. Min Act: -0.1700
Data Index: 4112966 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.8304. Min Act: -0.1700
Data Index: 416478 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.7679. Min Act: -0.1700
Data Index: 4160689 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.7366. Min Act: -0.1700
Data Index: 8462398 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.7054. Min Act: -0.1700
Data Index: 4491715 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.7054. Min Act: -0.1700
Data Index: 6255162 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.6741. Min Act: -0.1700
Data Index: 4828447 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.6741. Min Act: -0.1700
Data Index: 239231 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.6429. Min Act: -0.1700
Data Index: 7294124 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.6116. Min Act: -0.1700
Data Index: 4904660 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.6116. Min Act: -0.1700
Data Index: 4828445 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.5804. Min Act: -0.1700
Data Index: 4828446 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.5804. Min Act: -0.1700
Data Index: 8619491 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.5804. Min Act: -0.1700
Data Index: 3031309 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.5491. Min Act: -0.1700
Data Index: 2566168 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9866. Min Range: -5.9866
Max Act: 5.5491. Min Act: -0.1700
Data Index: 2428773 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19